GraphOS MCP Server

GetClientMetrics

Read-onlyIdempotent

Traffic broken down by client for a graph over a time window, as compact CSV. Columns: start timestamp, end exclusive timestamp, client name, client version, operation name, request count, request latency p50 ms, request latency p99 ms, request with error count. Answers which clients call a graph, which client versions are still on the wire, and which client drives errors or latency. Clients that do not report apollographql-client-name/-version come back with empty name and version columns. Ranked by orderBy descending: default REQUEST_COUNT (busiest); REQUEST_WITH_ERROR_COUNT for most error-prone, REQUEST_LATENCY_P99_MS for slowest. variantName and operationName scope to one or more variants or operations by exact name (omit for all). Rows are one per client + version + operation, so a busy graph has far more groups than the other metrics tools: scope by operationName or raise limit when a breakdown looks truncated. Keep the default resolution of ENTIRE_RANGE for totals and top-N, which gives one row per group ranked over the whole window. DAY/HOUR/MINUTE give one row per group per bucket ranked within each bucket, so a window total then needs a per-group sum plus a limit big enough to cover every bucket; too small a limit silently undercounts. Only HOUR and MINUTE accept a to of now, so use them for bursts in the last 24 hours. Avoid MONTH: it labels buckets by calendar month, not by the requested window.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`to`	Yes	The ending timestamp for the report. Must be in the format: 2025-01-01T08:00:00Z (ISO 8601).
`from`	Yes	The starting timestamp for the report. Must be in the format: 2025-01-01T00:00:00Z (ISO 8601).
`limit`	No	Maximum number of records to return (default: 100, max 10000).
`graphId`	Yes
`orderBy`	No		REQUEST_COUNT
`resolution`	No	The resolution of the time groups for the report. This resolution will affect the range of times that can be used for the 'from' and 'to' timestamps: - For the MINUTE resolution, the total time between 'from' and 'to' must be no more than 1 day, and the 'from' time must be no earlier than 30 days ago. - For the HOUR resolution, the total time between 'from' and 'to' must be no more than 7 days, and the 'from' time must be no earlier than 90 days ago. - For the DAY, MONTH, and ENTIRE_RANGE resolutions, the 'from' time must be no earlier than 549 days ago (approx 18 months), and the 'to' time must be no later than 1 day ago. If these criteria are not met, this will return a REQUEST_INVALID error.	ENTIRE_RANGE
`variantName`	No
`operationName`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`data`	No
`errors`	No
`extensions`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed17 schema fields changedSep 18, 2026

addedInput schema / properties / limit / anyOf

Added value: +[
+  {
+    "type": "integer"
+  },
+  {
+    "type": "null"
+  }
+]

addedInput schema / properties / limit / default
```
Added value: +50
```
removedInput schema / properties / limit / type
```
Removed value: -"integer"
```

addedInput schema / properties / operationName / anyOf

Added value: +[
+  {
+    "items": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "type": "array"
+  },
+  {
+    "type": "null"
+  }
+]

removedInput schema / properties / operationName / items

Removed value: -{
-  "oneOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ]
-}

removedInput schema / properties / operationName / type
```
Removed value: -"array"
```

removedInput schema / properties / orderBy / $ref

Removed value: -"#/definitions/OperationInsightsTimeseriesReportMetric"

addedInput schema / properties / orderBy / anyOf

Added value: +[
+  {
+    "$ref": "#/definitions/OperationInsightsTimeseriesReportMetric"
+  },
+  {
+    "type": "null"
+  }
+]

addedInput schema / properties / orderBy / default
```
Added value: +"REQUEST_COUNT"
```

removedInput schema / properties / resolution / $ref

Removed value: -"#/definitions/TimeseriesReportResolution"

addedInput schema / properties / resolution / anyOf

Added value: +[
+  {
+    "$ref": "#/definitions/TimeseriesReportResolution"
+  },
+  {
+    "type": "null"
+  }
+]

addedInput schema / properties / resolution / default
```
Added value: +"ENTIRE_RANGE"
```

addedInput schema / properties / variantName / anyOf

Added value: +[
+  {
+    "items": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "type": "array"
+  },
+  {
+    "type": "null"
+  }
+]

removedInput schema / properties / variantName / items

Removed value: -{
-  "oneOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ]
-}

removedInput schema / properties / variantName / type
```
Removed value: -"array"
```

addedOutput schema / properties / data / properties / graph / anyOf

Added value: +[
+  {
+    "properties": {
+      "operationInsightsTimeseriesReport": {
+        "description": " Returns a timeseries of operation metrics across a specified time range for this graph. This will return specified metrics (request count,\n avg latency, etc) grouped by time and the specified dimensions (query ID, query name, client name, etc). This API is rate limited and only\n allows a small number of requests per minute, and will return a RATE_LIMIT_EXCEEDED error if too many requests are made for a graph. If a\nrequest to this field times out, we recommend that you try a shorter time range or fewer dimensions.",
+        "properties": {
+          "csv": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "A CSV representation of the results. This includes a header and rows that have a column for start and end timestamp and all requested dimensions and metrics."
+          }
+        },
+        "type": "object"
+      }
+    },
+    "required": [
+      "operationInsightsTimeseriesReport"
+    ],
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]

removedOutput schema / properties / data / properties / graph / oneOf

Removed value: -[
-  {
-    "properties": {
-      "operationInsightsTimeseriesReport": {
-        "description": " Returns a timeseries of operation metrics across a specified time range for this graph. This will return specified metrics (request count,\n avg latency, etc) grouped by time and the specified dimensions (query ID, query name, client name, etc). This API is rate limited and only\n allows a small number of requests per minute, and will return a RATE_LIMIT_EXCEEDED error if too many requests are made for a graph. If a\nrequest to this field times out, we recommend that you try a shorter time range or fewer dimensions.",
-        "properties": {
-          "csv": {
-            "description": "A CSV representation of the results. This includes a header and rows that have a column for start and end timestamp and all requested dimensions and metrics.",
-            "oneOf": [
-              {
-                "type": "string"
-              },
-              {
-                "type": "null"
-              }
-            ]
-          }
-        },
-        "type": "object"
-      }
-    },
-    "required": [
-      "operationInsightsTimeseriesReport"
-    ],
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]

AddedSep 11, 2026

TDQS

A5/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description goes far beyond that by disclosing output specifics (CSV columns, empty client name/version), ranking behavior, row cardinality, silent undercounting when limit is too small, and calendar-month labeling for MONTH. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Although long, every sentence serves a distinct purpose: purpose, output format, default ranking, scoping, row cardinality, resolution behavior, limit warning, temporal constraints, and MONTH caveat. The most important information (purpose and output) is front-loaded, and nothing is redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's high complexity (8 params, multiple resolutions, ranking metrics, hidden truncation traps), the description is exceptionally complete. It covers behavioral caveats, default selections, and when to adjust parameters. An output schema exists for return values, so the prose need not describe the response structure.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 50%, and the description substantially compensates. It explains orderBy values and defaults (REQUEST_COUNT default, REQUEST_WITH_ERROR_COUNT for errors, REQUEST_LATENCY_P99_MS for slowest), resolution behavior and defaults, variantName/operationName exact-name scoping, and the limit truncation caveat. This meaningfully extends the raw parameter definitions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Traffic broken down by client for a graph over a time window, as compact CSV.' It then enumerates the exact questions it answers (which clients call a graph, which versions are on the wire, which drives errors/latency), clearly distinguishing it from sibling metrics tools like GetOperationMetrics or GetSubgraphMetrics.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit when-to-use guidance ('Answers which clients call a graph') and strong when-not-to-use guidance: avoid MONTH, only HOUR/MINUTE accept a 'to' of now, and warns that a busy graph has more groups than other metrics tools so users should scope by operationName or raise limit. This effectively routes the agent to the correct tool without opening sibling schemas.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All GraphOS MCP Server tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?